1B Parameter LLMs — Page 70

Llama-3.2-1B-Instruct-Chat-sft

ultrafeedback_binarized-alpaca-llama-3-1b-2-epochs-alpha-0.8-beta-0-2-epochs

Llama-3.2-1B-Instruct-cardio-semi-synth-annotation_r1_O1_f1_LT_zcr_bf16

Llama-3.2-1B-Turkish-Instruct

finetuned_modelo9

Drummond-1b1-Instruct

main14

trt1

K220

mja2

DeepSeek-R1-Distill-Qwen-1.5B-GRPO

Qwen-1.5B_THIP_GRPO

zone

gemma-3-finetune

merge_linear_cos0.9fmt0.1_MRL4096_ROLLOUT4_LR1e-6

merge_accfmt_MRL4096_ROLLOUT4_LR5e-7_w0.9_linear

merge_cosfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_linear

merge_lenfmt_MRL4096_ROLLOUT4_LR5e-7_w0.7_linear

merge_accfmt_MRL4096_ROLLOUT4_LR1e-6_w0.5_ties

gemma-3-1b-it-code-hint-3

merge_lenfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_ties_density0.2

Qwen2.5-Math-1.5B

SmolLM3-Mid-Second-Round

45719427

qwen1.5b-myanmar-cpt-final

math_merge_linear_1.5B

gemma3-fine-tuned

alpha_0.4_DeepSeek-R1-Distill-Qwen-1.5B

3f31e361

qwen15_code200tok_step1750

WitchLM-1.5B

r7

gemma-3-1b-it-PT-SynthDolly-2A

StudyAiv19

gemma-3-1b-it-preference_dataset_mixture2_and_safe_pku-Preference

qwen2.5-math-1.5B-base

Qwen2.5-1.5B-SFT-Schwinn

qwen25-1.5b_ultrafeedback_sft_lr1e-4

AGiXT-AbilitySelect-270m

sub38-221

Qwen2.5-1.5B-DPO-BestOfN-Schwinn-v7

nb-notram-llama-3.2-1b-instruct